R Notebook

library(tidyverse)

tidyverse_logo()

* __  _    __   .    o           *  . 
 / /_(_)__/ /_ ___  _____ _______ ___ 
/ __/ / _  / // / |/ / -_) __(_-</ -_)
\__/_/\_,_/\_, /|___/\__/_/ /___/\__/ 
     *  . /___/      o      .       * 

if restarted R and just want one part or tidyverse

tidyverse::tidyverse_logo()

* __  _    __   .    o           *  . 
 / /_(_)__/ /_ ___  _____ _______ ___ 
/ __/ / _  / // / |/ / -_) __(_-</ -_)
\__/_/\_,_/\_, /|___/\__/_/ /___/\__/ 
     *  . /___/      o      .       * 

devtools::install_github("codeclan/CodeClanData")

WARNING: Rtools is required to build R packages, but is not currently installed.

Please download and install Rtools 4.0 from https://cran.r-project.org/bin/windows/Rtools/.
Skipping install of 'CodeClanData' from a github remote, the SHA1 (d46cb3c5) has not changed since last install.
  Use `force = TRUE` to force installation

library(CodeClanData)

students

Working with dplyr

all_deaths

#checking our data

#number of rows
nrow(all_deaths)

[1] 917

#number of colums
ncol(all_deaths)

[1] 13

# overall dimensions
dim(all_deaths)

[1] 917  13

# variable names
names(all_deaths)

 [1] "name"               "allegiances"        "year_of_death"      "book_of_death"     
 [5] "death_chapter"      "book_intro_chapter" "gender"             "nobility"          
 [9] "book1_GoT"          "book2_CoK"          "book3_SoS"          "book4_FfC"         
[13] "book5_DwD"         

# check the first 10 rows
head(all_deaths, 10)

# check the last 10
tail(all_deaths, 10)

# get an overveiw of the data
glimpse(all_deaths)

Rows: 917
Columns: 13
$ name               <chr> "Addam Marbrand", "Aegon Frey (Jinglebell)", "Aegon Targaryen", "Adrack Hum~
$ allegiances        <chr> "Lannister", "None", "House Targaryen", "House Greyjoy", "Lannister", "Bara~
$ year_of_death      <dbl> NA, 299, NA, 300, NA, NA, 300, 300, NA, NA, 299, NA, 300, NA, NA, NA, 299, ~
$ book_of_death      <dbl> NA, 3, NA, 5, NA, NA, 4, 5, NA, NA, 2, NA, 5, NA, NA, NA, 2, NA, NA, 4, NA,~
$ death_chapter      <dbl> NA, 51, NA, 20, NA, NA, 35, NA, NA, NA, 56, NA, 4, NA, NA, NA, 46, NA, NA, ~
$ book_intro_chapter <dbl> 56, 49, 5, 20, NA, NA, 21, 59, 11, 0, 50, 54, 18, 15, 38, 26, 4, 6, 65, 36,~
$ gender             <dbl> 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, ~
$ nobility           <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, ~
$ book1_GoT          <dbl> 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 1, ~
$ book2_CoK          <dbl> 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, ~
$ book3_SoS          <dbl> 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, ~
$ book4_FfC          <dbl> 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, ~
$ book5_DwD          <dbl> 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, ~

# view data
view(all_deaths)

#view a shirt representation of the data
str(all_deaths)

spec_tbl_df [917 x 13] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ name              : chr [1:917] "Addam Marbrand" "Aegon Frey (Jinglebell)" "Aegon Targaryen" "Adrack Humble" ...
 $ allegiances       : chr [1:917] "Lannister" "None" "House Targaryen" "House Greyjoy" ...
 $ year_of_death     : num [1:917] NA 299 NA 300 NA NA 300 300 NA NA ...
 $ book_of_death     : num [1:917] NA 3 NA 5 NA NA 4 5 NA NA ...
 $ death_chapter     : num [1:917] NA 51 NA 20 NA NA 35 NA NA NA ...
 $ book_intro_chapter: num [1:917] 56 49 5 20 NA NA 21 59 11 0 ...
 $ gender            : num [1:917] 1 1 1 1 1 1 1 0 1 1 ...
 $ nobility          : num [1:917] 1 1 1 1 1 1 1 1 1 0 ...
 $ book1_GoT         : num [1:917] 1 0 0 0 0 0 1 1 0 0 ...
 $ book2_CoK         : num [1:917] 1 0 0 0 0 1 0 1 1 0 ...
 $ book3_SoS         : num [1:917] 1 1 0 0 1 1 1 1 0 1 ...
 $ book4_FfC         : num [1:917] 1 0 0 0 0 0 1 0 1 0 ...
 $ book5_DwD         : num [1:917] 0 0 1 1 0 0 0 1 0 0 ...
 - attr(*, "spec")=
  .. cols(
  ..   name = col_character(),
  ..   allegiances = col_character(),
  ..   year_of_death = col_double(),
  ..   book_of_death = col_double(),
  ..   death_chapter = col_double(),
  ..   book_intro_chapter = col_double(),
  ..   gender = col_double(),
  ..   nobility = col_double(),
  ..   book1_GoT = col_double(),
  ..   book2_CoK = col_double(),
  ..   book3_SoS = col_double(),
  ..   book4_FfC = col_double(),
  ..   book5_DwD = col_double()
  .. )

# print data in the console
all_deaths

Select()

# selecting a few variables to keep
select(all_deaths, name, allegiances, gender, nobility, year_of_death)

# can remove a colum if needed
select(all_deaths, -name)

# making a var 
death_no_names <- select(all_deaths, -name)

books <- select(all_deaths, 4, 6, 9:13)
books

books_anotherway <- select(all_deaths, 4, 6, book1_GoT:book5_DwD)
books_anotherway

god <- select(all_deaths, contains("book"))
god

deaths <- select(all_deaths, 3:5)
deaths

filter()

filter(all_deaths, allegiances == "Lannister")

# found 102 rows
filter(all_deaths, allegiances == "Lannister" | 
         allegiances == "House Lannister")

filter(all_deaths, allegiances != "Lannister")

filter(all_deaths, allegiances %in% c("House Lannister", 
                                      "Lannister"))

filter(all_deaths, year_of_death >= 299)

filter(all_deaths, allegiances == "None")

filter(all_deaths, book_intro_chapter >= 5 & 
         book_intro_chapter <= 10)

#Tast 1 Find where the year_of_deathis less than or equal to 299.

filter(all_deaths, year_of_death <= 299)

#Tast 2 Find the females (gender is 0) who are not Lannisters

filter(all_deaths, gender == 0 & allegiances != "Lannister")

#Tast 3 Find just the data for the characters “Jon Snow”, “Daenerys Targaryen” and “Samwell Tarly”.

filter(all_deaths, name == "Jon Snow" |
           name == "Daenerys Targaryen" |
           name == "Samwell Tarly")

another way

filter(all_deaths, name %in% c("Jon Snow",
                               "Daenerys Targaryen",
                               "Samwell Tarly"))

Arrange

arrange(all_deaths, gender)

arrange(all_deaths, desc(gender))

arrange(all_deaths, book_of_death, death_chapter)

#Arrange all_deaths by allegiances. What happens when you arrange by a character column?

arrange(all_deaths, allegiances)

#Arrange all_deaths by allegiances and book_intro_chapter

arrange(all_deaths, allegiances, book_intro_chapter)

#Arrange all_deaths by descending year_of_death

arrange(all_deaths, desc(year_of_death))

mutate()

# To make a new var/change a var
mutate(all_deaths, years_survived = year_of_death - 298)

mutate(all_deaths, book_of_death = book_of_death * 5)

mutate(all_deaths, year_of_death = is.na(year_of_death))

# changes year_of_death from dbl to a Lgl

mutate(all_deaths, book_of_death = as.character(book_of_death))

mutate(all_deaths, name = as.numeric(name))

Warning: Problem with `mutate()` column `name`.
i `name = as.numeric(name)`.
i NAs introduced by coercion

mutate(all_deaths, year_of_death = sum(year_of_death, na.rm = TRUE))

mutate( all_deaths, year_of_death = mean(year_of_death, na.rm = TRUE))

Summarise

summarise(all_deaths, n_males = sum(gender))

death_grouped <- group_by(all_deaths, allegiances)
death_grouped

# is the background Groups:allegiances [21]
summarise(death_grouped, character_count = n())

death_grouped <- group_by(all_deaths, nobility, gender)
summarise(death_grouped, character_count = n())

`summarise()` has grouped output by 'nobility'. You can override using the `.groups` argument.

magrittr pipes

# find the people taht have died
have_died <- filter(all_deaths, !is.na(book_of_death))

died_grouped <-  group_by(have_died, allegiances)

died_counts <- summarise(died_grouped, count = n())

arrange(died_counts, desc(count))

# takes the line before the %>% and places as the first argument
all_deaths %>%
  filter(!is.na(book_of_death)) %>%
  group_by(allegiances) %>%
  summarise(count = n()) %>%
  arrange(desc(count))

# docent need to make mutual var

death_by_allegiance <- all_deaths %>%
                            filter(!is.na(book_of_death)) %>%
                            group_by(allegiances) %>%
                            summarise(count = n()) %>%
                            arrange(desc(count))

Pull

av_year_of_death <- all_deaths %>%
  summarise(av_value = mean(year_of_death, 
                            na.rm = TRUE))

av_year_of_death

all_deaths %>%
  mutate(death_later_than_av = year_of_death >
           av_year_of_death)

all_deaths %>%
  mutate(death_later_than_av = year_of_death >
           299.1574)

class(av_year_of_death)

[1] "numeric"

class(299.1574)

[1] "numeric"

av_year_of_death <- all_deaths %>%
  summarise(av_value = mean(year_of_death, 
                            na.rm = TRUE)) %>%
  pull()

av_year_of_death

[1] 299.1574

all_deaths %>%
  mutate(death_later_than_av = year_of_death >
           av_year_of_death)